Presenter Email
michael.sawyer@forthillgroup.com
Submission Type
Poster
Topic Area
Aviation Mental Health
Topic Area
Aviation Mental Health
Keywords
Aviation Safety, Mental Health, Machine Learning, Natural Language Processing, Voluntary Safety Reporting Programs, Human Factors
Abstract
Voluntary Safety Reporting Programs (VSRPs) are a critical tool in the aviation industry for monitoring safety issues observed by the frontline workforce. While VSRPs primarily focus on operational safety, report narratives often describe factors such as fatigue, workload, culture, staffing, and health, directly or indirectly impacting mental health. These reports can provide individual and organizational insights into aviation personnel's physical and psychological well-being. This poster introduces the AVIation Analytic Neural network for Safety events (AVIAN-S) model as a potential tool to extract and monitor these insights. AVIAN-S is a novel machine-learning model that leverages natural language processing (NLP) to analyze and label human factors in aviation safety reports efficiently and effectively. The AVIAN-S model was trained on over 70,000 manually classified aviation safety reporting data rows. It has demonstrated preliminary real-world accuracy in the range of 89%-97% depending on the factor measured and random split of training data as indicated by the TopKCategoricalAccuracy measurement (k=9). While AVIAN-S was developed to label reports based on a human factors taxonomy, the relationship between these factors and mental health means it can be extended to identify potential mental health indicators reported by the operational workforce. The poster discusses the development and training of the AVIAN-S model and its potential application in identifying mental health indicators. Applying the model to identify these indicators offers the potential to enhance the industry's capacity to monitor and address factors that impact the psychological safety of its workforce.
Included in
Artificial Intelligence and Robotics Commons, Aviation Safety and Security Commons, Human Factors Psychology Commons
Using Natural Language Processing to Identify Mental Health Indicators in Aviation Voluntary Safety Reports
Voluntary Safety Reporting Programs (VSRPs) are a critical tool in the aviation industry for monitoring safety issues observed by the frontline workforce. While VSRPs primarily focus on operational safety, report narratives often describe factors such as fatigue, workload, culture, staffing, and health, directly or indirectly impacting mental health. These reports can provide individual and organizational insights into aviation personnel's physical and psychological well-being. This poster introduces the AVIation Analytic Neural network for Safety events (AVIAN-S) model as a potential tool to extract and monitor these insights. AVIAN-S is a novel machine-learning model that leverages natural language processing (NLP) to analyze and label human factors in aviation safety reports efficiently and effectively. The AVIAN-S model was trained on over 70,000 manually classified aviation safety reporting data rows. It has demonstrated preliminary real-world accuracy in the range of 89%-97% depending on the factor measured and random split of training data as indicated by the TopKCategoricalAccuracy measurement (k=9). While AVIAN-S was developed to label reports based on a human factors taxonomy, the relationship between these factors and mental health means it can be extended to identify potential mental health indicators reported by the operational workforce. The poster discusses the development and training of the AVIAN-S model and its potential application in identifying mental health indicators. Applying the model to identify these indicators offers the potential to enhance the industry's capacity to monitor and address factors that impact the psychological safety of its workforce.
